Discrete Contrastive Learning for Diffusion Policies in Autonomous Driving
This work addresses the problem of realistic human driver simulation for autonomous vehicle testing, which is incremental as it builds on existing diffusion and contrastive learning methods.
The paper tackled the challenge of simulating diverse human driving behaviors for autonomous vehicle testing by proposing a discrete contrastive learning approach to extract driving styles from data and using them to condition a diffusion policy. The result showed that the generated behaviors are safer and more human-like than baseline methods, as confirmed by empirical evaluation.
Learning to perform accurate and rich simulations of human driving behaviors from data for autonomous vehicle testing remains challenging due to human driving styles' high diversity and variance. We address this challenge by proposing a novel approach that leverages contrastive learning to extract a dictionary of driving styles from pre-existing human driving data. We discretize these styles with quantization, and the styles are used to learn a conditional diffusion policy for simulating human drivers. Our empirical evaluation confirms that the behaviors generated by our approach are both safer and more human-like than those of the machine-learning-based baseline methods. We believe this has the potential to enable higher realism and more effective techniques for evaluating and improving the performance of autonomous vehicles.